GPT-5.5 Instant (June 2026)
Jun 2026
GPT-5.5 Instant (June 2026)Compare inon
Benchmarks of GPT-5.5 Instant (June 2026)16
BenchmarkByScoreRank
Overall1
Knowledge3
Science3
Coding2
Agents4
Documents2
Legacy · saturated or no longer reported1
No benchmark matches
$0.69per task?
API price not publicprice
167 tok/sfirst token in 0.9 s?
400Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT-6.1 Solxhigh+96%-43%$0.39Remove unsupported parameters+5BetterGPT-6 Lunamedium+15%-97%$0.017Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking+78%-81%$0.13Pass back reasoning_content+3
CheaperDeepSeek V4.1 Flash 1017maxOpen+73%-62%$0.26Pass back reasoning_content · Chat Completions+4CheaperGPT-6 Solxhigh+70%-25%$0.52ModelScoreCostPer taskWhat changes
GPT-6.1 Solxhigh+96%-43%$0.39Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen+78%-81%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen+73%-62%$0.26Pass back reasoning_content · Chat Completions+4GPT-6 Solxhigh+70%-25%$0.52
Claude Haiku 5.5max+67%-69%$0.21Remove sampling parameters+5ModelScoreCostPer taskWhat changes
GPT-6 Lunamedium+15%-97%$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+13%-96%$0.024Remove sampling parameters+5GPT-5.6 Lunahigh+23%-94%$0.044MiMo v2.6 FlashthinkingOpen+46%-91%$0.062Pass back reasoning_content+3GPT-6.1 Sollow+62%-81%$0.13Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+78%-81%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen+73%-62%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+72%+190%$2.01No image input+4
Step 5 PreviewthinkingOpen+68%+48%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+68%+189%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astramedium+91%+123%$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium+84%-69%$0.21Remove unsupported parameters+5GPT-6 Solmedium+53%-64%$0.25GPT-5.6 Solmedium+51%-27%$0.50GPT-5.5medium+30%+30%$0.90Prompts with >272K input tokensGPT-5.3 Codexxhigh+25%—$1.75 / $14DeprecatedGPT-5.6 Terramedium+16%-73%$0.18Prompts with >272K input tokensGPT-6 Lunamedium+15%-97%$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
2 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam19.9#125
AA Omniscience Index3.7#57
CritPt (physics)0#180
AA Omniscience · Accuracy44.4#35
GDP.pdf · AA all-pass20.2#25
GPQA Diamond82.3#103
Coding
Terminal-Bench 4.012.6#34
SciCode52.5#39
Terminal-Bench 2.134.8#93
Agents & Tool Use
AutomationBench-AA36.4#46
GDPval-AA (work tasks) 2.10.5#121
τ³-Banking · AA11.8#85
AA-Briefcase 1.1 · Elo1,086.4#50
FAQ
How much does GPT-5.5 Instant (June 2026) cost?›
There is no per-unit API price: API price not public.
Is GPT-5.5 Instant (June 2026) free to use?›
There is no free API.
How good is GPT-5.5 Instant (June 2026), and what is it best at?›
#125 of 334 in Chat & Knowledge, #34 of 132 in Coding, #46 of 133 in Agents & Tool Use, #25 of 133 in Vision & Documents. Strongest at: Knowledge.
Is GPT-5.5 Instant (June 2026) better than GPT-5.5 Instant (May 2026)?›
On AA Intelligence Index 4.3.2, GPT-5.5 Instant (June 2026) scores 26 vs 22.7 — higher.
What is the context window of GPT-5.5 Instant (June 2026)?›
400K tokens.
When was GPT-5.5 Instant (June 2026) released? Is there a newer version?›
Released 2026-06-25. It is the current version in its line.
Is GPT-5.5 Instant (June 2026) open source?›
No, GPT-5.5 Instant (June 2026) is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-5.5 Instant (June 2026) read images?›
It accepts text and images as input.
What is GPT-5.5 Instant (June 2026)?›
GPT-5.5 Instant (June 2026) is a closed language model from OpenAI, released Jun 2026, the successor to GPT-5.5 Instant (May 2026).
What are the best alternatives to GPT-5.5 Instant (June 2026)?›
GPT-6.1 Sol (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).